初始化项目，由ModelHub XC社区提供模型

Model: prithivMLmods/Omni-Reasoner3-Merged
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,49 @@
+---
+base_model:
+- prithivMLmods/Llama-Doctor-3.2-3B-Instruct
+- prithivMLmods/Codepy-Deepthink-3B
+- prithivMLmods/Llama-Deepsync-3B
+- prithivMLmods/Llama-Sentient-3.2-3B-Instruct
+- prithivMLmods/Llama-Magpie-3.2-3B-Instruct
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+![omni.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/dTvAZ4d3o3ZbDtG_kk6z3.png)
+
+# **Merge Llama Based** 
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [prithivMLmods/Llama-Deepsync-3B](https://huggingface.co/prithivMLmods/Llama-Deepsync-3B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [prithivMLmods/Llama-Doctor-3.2-3B-Instruct](https://huggingface.co/prithivMLmods/Llama-Doctor-3.2-3B-Instruct)
+* [prithivMLmods/Codepy-Deepthink-3B](https://huggingface.co/prithivMLmods/Codepy-Deepthink-3B)
+* [prithivMLmods/Llama-Sentient-3.2-3B-Instruct](https://huggingface.co/prithivMLmods/Llama-Sentient-3.2-3B-Instruct)
+* [prithivMLmods/Llama-Magpie-3.2-3B-Instruct](https://huggingface.co/prithivMLmods/Llama-Magpie-3.2-3B-Instruct)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: prithivMLmods/Llama-Magpie-3.2-3B-Instruct
+  - model: prithivMLmods/Codepy-Deepthink-3B
+  - model: prithivMLmods/Llama-Doctor-3.2-3B-Instruct
+  - model: prithivMLmods/Llama-Sentient-3.2-3B-Instruct
+  - model: prithivMLmods/Llama-Magpie-3.2-3B-Instruct
+  - model: prithivMLmods/Llama-Deepsync-3B
+merge_method: model_stock
+base_model: prithivMLmods/Llama-Deepsync-3B
+normalize: true
+int8_mask: true
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "prithivMLmods/Llama-Deepsync-3B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

mergekit_config.yml

@@ -0,0 +1,12 @@
+models:
+  - model: prithivMLmods/Llama-Magpie-3.2-3B-Instruct
+  - model: prithivMLmods/Codepy-Deepthink-3B
+  - model: prithivMLmods/Llama-Doctor-3.2-3B-Instruct
+  - model: prithivMLmods/Llama-Sentient-3.2-3B-Instruct
+  - model: prithivMLmods/Llama-Magpie-3.2-3B-Instruct
+  - model: prithivMLmods/Llama-Deepsync-3B
+merge_method: model_stock
+base_model: prithivMLmods/Llama-Deepsync-3B
+normalize: true
+int8_mask: true
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fce30f1a9a3a52560cf3df782c7cca38ad8e1d485cf5a7c4b398dcea3bc9e6
+size 4990977384

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2d2f0871c73f55c873c8fcbcf0689d6b41caa7e3bd0e3fa82b93010fefae85
+size 1434551664

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}